Predictive Utility of a Machine Learning Algorithm in Estimating Mortality Risk in Cardiac Surgery

Background: This study evaluated the predictive utility of a machine learning algorithm in estimating operative mortality risk in cardiac surgery.

Methods: Index adult cardiac operations performed between 2011 and 2017 at a single institution were included. The primary outcome was operative mortality. Extreme gradient boosting (XGBoost) models were developed and evaluated using 10-fold cross-validation with 1000-replication bootstrapping. Model performance was assessed using multiple measures including precision, recall, calibration plots, area under the receiver-operating characteristic curve (C-index), accuracy, and F1 score.

Results: A total of 11,190 patients were included (7048 isolated coronary artery bypass grafting [CABG], 2507 isolated valves, and 1635 CABG plus valves). The Society of Thoracic Surgeons Predicted Risk of Mortality (STS PROM) was 3.2% ± 5.0%. Actual operative mortality was 2.8%. There was moderate correlation (r = 0.652) in predicted risk between XGBoost and STS PROM for the overall cohort and weak correlation (r = 0.473) in predicted risk between the models specifically in patients with operative mortality. XGBoost demonstrated improvements in all measures of model performance when compared with the STS PROM in the validation cohorts: mean average precision (0.221 XGBoost vs 0.180 STS PROM), C-index (0.808 XGBoost vs 0.795 STS PROM), calibration (mean observed-to-expected mortality: XGBoost 0.993 vs 0.956 STS PROM), accuracy (1%-3% improvement across discriminatory thresholds of 3%-10% risk), and F1 score (0.281 XGBoost vs 0.230 STS PROM).

Conclusions: Machine learning algorithms such as XGBoost have promise in predictive analytics in cardiac surgery. The modest improvements in model performance demonstrated in the current study warrant further validation in larger cohorts of patients.